Thursday, October 29, 2026 🏢 AI Companies Hub RSS About Contact Admin
POPULAR BEATS: Generative AI LLMs & NLP Autonomous Agents Robotics & Hardware Enterprise AI AI Ethics & Policy 🏢 All AI Companies

SmolLM2 1.7B

On-Device Compact Transformer
Official Source & Paper
Hugging Face logo Hugging Face 📄 Open Weights (Apache 2.0) 🌍 Global (Global) 🗓️ Effective Date: 01.11.2024

Ultra-lightweight open model trained on 11 trillion tokens, capable of running inside web browsers via WebGPU or on mobile smartphones.

Model Size / Parameters 1.71B Dense Architecture: On-Device Compact Transformer
Context Window (Input) 8,192 tokens Token Capacity
Max Output Tokens 2,048 tokens Single Generation Limit
Supported Modalities Text, Code Native Multimodal Ingestion
License & Access Open Weights (Apache 2.0) Open Weights vs. API
Release Date November 2024 Effective Date: 01.11.2024

Verified Benchmark Results

Standardized academic and industry evaluation benchmarks (Effective Date: 01.11.2024).

MMLU-Pro / 5-Shot General Intellect
65.2%
SWE-bench Verified Software Engineering
18.4%
MATH 500 / AIME Mathematical Reasoning
54.0%
GPQA Diamond Doctoral Science
29.5%
HumanEval / Python Algorithm Synthesis
62.8%

Pricing & Cost Efficiency

Official API token pricing and self-hosted licensing terms.

Input Pricing (Prompt)
Free / Self-Hosted
Per 1 million processed tokens
Output Pricing (Generation)
Free / Self-Hosted
Per 1 million generated tokens
Verified Datasheet: Source: Hugging Face Research Documentation • Effective Date: 01.11.2024
← Back to All AI Model Datasheets

Latest Coverage & Analysis on SmolLM2 1.7B